Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 127494
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    specific details about individuals' physical traits and activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron doesn’t reliably activate on any input patterns—it’s essentially “dead” and never responds.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eudicots
    -0.07
     perf
    -0.07
     Flush
    -0.07
    usement
    -0.06
    aucoup
    -0.06
     IPL
    -0.06
    ...")↵
    -0.06
     BT
    -0.06
     ох
    -0.06
     satin
    -0.06
    POSITIVE LOGITS
    /live
    0.07
     francaise
    0.07
     :)
    0.07
    (ticket
    0.06
    нили
    0.06
    чается
    0.06
    (dirname
    0.06
    +',
    0.06
     pelic
    0.06
     Votes
    0.06
    Activations Density 0.238%

    No Known Activations